Markdown json will cause the ledger information parse failed.

[qmkCamel]

What happened?

Describe the bug
When I use the MagenticOneGroupChat and gpt-4o to build something, found a little problem.
The ORCHESTRATOR_PROGRESS_LEDGER_PROMPT required the model_client output json format as below

Please output an answer in pure JSON format according to the following schema. 
The JSON object must be parsable as-is. 
DO NOT OUTPUT ANYTHING OTHER THAN JSON, AND DO NOT DEVIATE FROM THIS SCHEMA:

    {{
       "is_request_satisfied": {{
            "reason": string,
            "answer": boolean
        }},
        "is_in_loop": {{
            "reason": string,
            "answer": boolean
        }},
        "is_progress_being_made": {{
            "reason": string,
            "answer": boolean
        }},
        "next_speaker": {{
            "reason": string,
            "answer": string (select from: {names})
        }},
        "instruction_or_question": {{
            "reason": string,
            "answer": string
        }}
    }}

but the result is markdown format json like this and it will cause the team chat failed

{
  "content": "```json {...}"
}

To Reproduce
MagenticGroupChat and gpt-4o

ERROR:src.da_agent_magentic:群聊执行失败: Failed to parse ledger information after multiple retries.
Traceback (most recent call last):
  File "/agent_demo/src/da_agent_magentic.py", line 100, in analyze_data_file
    await Console(team.run_stream(task=task_description))
  File "/agent_demo/.venv/lib/python3.10/site-packages/autogen_agentchat/ui/_console.py", line 117, in Console
    async for message in stream:
  File "/agent_demo/.venv/lib/python3.10/site-packages/autogen_agentchat/teams/_group_chat/_base_group_chat.py", line 499, in run_stream
    await self._runtime.send_message(
  File "/agent_demo/.venv/lib/python3.10/site-packages/autogen_core/_single_threaded_agent_runtime.py", line 332, in send_message
    return await future
  File "/agent_demo/.venv/lib/python3.10/site-packages/autogen_core/_single_threaded_agent_runtime.py", line 445, in _process_send
    response = await recipient_agent.on_message(
  File "/agent_demo/.venv/lib/python3.10/site-packages/autogen_core/_base_agent.py", line 113, in on_message
    return await self.on_message_impl(message, ctx)
  File "/agent_demo/.venv/lib/python3.10/site-packages/autogen_agentchat/teams/_group_chat/_sequential_routed_agent.py", line 67, in on_message_impl
    return await super().on_message_impl(message, ctx)
  File "/agent_demo/.venv/lib/python3.10/site-packages/autogen_core/_routed_agent.py", line 485, in on_message_impl
    return await h(self, message, ctx)
  File "/agent_demo/.venv/lib/python3.10/site-packages/autogen_core/_routed_agent.py", line 389, in wrapper
    return_value = await func(self, message, ctx)
  File "/agent_demo/.venv/lib/python3.10/site-packages/autogen_agentchat/teams/_group_chat/_magentic_one/_magentic_one_orchestrator.py", line 186, in handle_start
    await self._reenter_outer_loop(ctx.cancellation_token)
  File "/agent_demo/.venv/lib/python3.10/site-packages/autogen_agentchat/teams/_group_chat/_magentic_one/_magentic_one_orchestrator.py", line 283, in _reenter_outer_loop
    await self._orchestrate_step(cancellation_token=cancellation_token)
  File "/agent_demo/.venv/lib/python3.10/site-packages/autogen_agentchat/teams/_group_chat/_magentic_one/_magentic_one_orchestrator.py", line 353, in _orchestrate_ste
    raise ValueError("Failed to parse ledger information after multiple retries.")

Expected behavior
The output should just as the prompt requires, just pure json.

{
  "content": "{...}"
}

Additional context

When the ORCHESTRATOR_PROGRESS_LEDGER_PROMPT prompt add the following content, the issue will not appear any more.

DO NOT OUTPUT MARKDOWN FORMAT JSON

It should like below

Please output an answer in pure JSON format according to the following schema. 
The JSON object must be parsable as-is. 
DO NOT OUTPUT ANYTHING OTHER THAN JSON, 
DO NOT OUTPUT MARKDOWN FORMAT JSON, 
AND DO NOT DEVIATE FROM THIS SCHEMA
...

Which packages was the bug in?

Python AgentChat (autogen-agentchat>=0.4.0)

AutoGen library version.

Python 0.5.6

Other library version.

No response

Model used

gpt-4o

Model provider

OpenAI

Other model provider

No response

Python version

3.10

.NET version

None

Operating system

MacOS

[ekzhu]

#6540 Use structured output should help also.

[qmkCamel]

#6540 Use structured output should help also.

Some models doesn't support structured output now, so may be the prompt opt is a general way.